| { | |
| "best_metric": 1.9274845123291016, | |
| "best_model_checkpoint": "./model_tweets_2020_Q2_75/checkpoint-2368000", | |
| "epoch": 20.210526315789473, | |
| "eval_steps": 8000, | |
| "global_step": 2400000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.2326369285583496, | |
| "eval_runtime": 109.1141, | |
| "eval_samples_per_second": 916.472, | |
| "eval_steps_per_second": 57.279, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.0726666666666665e-07, | |
| "loss": 2.407, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 2.1531760692596436, | |
| "eval_runtime": 109.5721, | |
| "eval_samples_per_second": 912.641, | |
| "eval_steps_per_second": 57.04, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 2.1194541454315186, | |
| "eval_runtime": 109.8202, | |
| "eval_samples_per_second": 910.579, | |
| "eval_steps_per_second": 56.911, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.0453333333333336e-07, | |
| "loss": 2.23, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 2.0944020748138428, | |
| "eval_runtime": 109.9526, | |
| "eval_samples_per_second": 909.483, | |
| "eval_steps_per_second": 56.843, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 2.0625503063201904, | |
| "eval_runtime": 109.6461, | |
| "eval_samples_per_second": 912.025, | |
| "eval_steps_per_second": 57.002, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.018e-07, | |
| "loss": 2.1798, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 2.0516622066497803, | |
| "eval_runtime": 110.2889, | |
| "eval_samples_per_second": 906.71, | |
| "eval_steps_per_second": 56.669, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 2.0354814529418945, | |
| "eval_runtime": 109.7487, | |
| "eval_samples_per_second": 911.173, | |
| "eval_steps_per_second": 56.948, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 3.9906666666666667e-07, | |
| "loss": 2.1621, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 2.0469346046447754, | |
| "eval_runtime": 109.2938, | |
| "eval_samples_per_second": 914.965, | |
| "eval_steps_per_second": 57.185, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 2.0306453704833984, | |
| "eval_runtime": 109.5416, | |
| "eval_samples_per_second": 912.895, | |
| "eval_steps_per_second": 57.056, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.963333333333333e-07, | |
| "loss": 2.1419, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 2.018167018890381, | |
| "eval_runtime": 109.7315, | |
| "eval_samples_per_second": 911.315, | |
| "eval_steps_per_second": 56.957, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 2.0107083320617676, | |
| "eval_runtime": 109.0625, | |
| "eval_samples_per_second": 916.905, | |
| "eval_steps_per_second": 57.307, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.936e-07, | |
| "loss": 2.1264, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 2.0096383094787598, | |
| "eval_runtime": 109.3127, | |
| "eval_samples_per_second": 914.807, | |
| "eval_steps_per_second": 57.175, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 2.010380506515503, | |
| "eval_runtime": 110.6854, | |
| "eval_samples_per_second": 903.462, | |
| "eval_steps_per_second": 56.466, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.908666666666667e-07, | |
| "loss": 2.1203, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 2.003709077835083, | |
| "eval_runtime": 109.0039, | |
| "eval_samples_per_second": 917.399, | |
| "eval_steps_per_second": 57.337, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 2.0078485012054443, | |
| "eval_runtime": 109.4142, | |
| "eval_samples_per_second": 913.958, | |
| "eval_steps_per_second": 57.122, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.8813333333333334e-07, | |
| "loss": 2.1116, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "eval_loss": 1.9965349435806274, | |
| "eval_runtime": 109.9802, | |
| "eval_samples_per_second": 909.255, | |
| "eval_steps_per_second": 56.828, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_loss": 2.0025391578674316, | |
| "eval_runtime": 110.9711, | |
| "eval_samples_per_second": 901.135, | |
| "eval_steps_per_second": 56.321, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 3.854e-07, | |
| "loss": 2.1041, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_loss": 1.992916464805603, | |
| "eval_runtime": 110.9498, | |
| "eval_samples_per_second": 901.309, | |
| "eval_steps_per_second": 56.332, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_loss": 1.9869908094406128, | |
| "eval_runtime": 109.4965, | |
| "eval_samples_per_second": 913.272, | |
| "eval_steps_per_second": 57.079, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 3.8266666666666665e-07, | |
| "loss": 2.1058, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_loss": 1.9895384311676025, | |
| "eval_runtime": 109.4386, | |
| "eval_samples_per_second": 913.755, | |
| "eval_steps_per_second": 57.11, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "eval_loss": 1.9794731140136719, | |
| "eval_runtime": 110.027, | |
| "eval_samples_per_second": 908.868, | |
| "eval_steps_per_second": 56.804, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 3.799333333333333e-07, | |
| "loss": 2.1064, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 1.9892573356628418, | |
| "eval_runtime": 109.3598, | |
| "eval_samples_per_second": 914.413, | |
| "eval_steps_per_second": 57.151, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "eval_loss": 1.9877266883850098, | |
| "eval_runtime": 110.3406, | |
| "eval_samples_per_second": 906.284, | |
| "eval_steps_per_second": 56.643, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 3.772e-07, | |
| "loss": 2.098, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "eval_loss": 1.9919915199279785, | |
| "eval_runtime": 110.6856, | |
| "eval_samples_per_second": 903.46, | |
| "eval_steps_per_second": 56.466, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "eval_loss": 1.9800524711608887, | |
| "eval_runtime": 110.1564, | |
| "eval_samples_per_second": 907.8, | |
| "eval_steps_per_second": 56.738, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.7446666666666667e-07, | |
| "loss": 2.0916, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_loss": 1.9778263568878174, | |
| "eval_runtime": 110.0821, | |
| "eval_samples_per_second": 908.413, | |
| "eval_steps_per_second": 56.776, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "eval_loss": 1.9744561910629272, | |
| "eval_runtime": 110.1318, | |
| "eval_samples_per_second": 908.003, | |
| "eval_steps_per_second": 56.75, | |
| "step": 216000 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 3.7173333333333333e-07, | |
| "loss": 2.0951, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "eval_loss": 1.9831310510635376, | |
| "eval_runtime": 110.3219, | |
| "eval_samples_per_second": 906.438, | |
| "eval_steps_per_second": 56.652, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "eval_loss": 1.9748752117156982, | |
| "eval_runtime": 109.9764, | |
| "eval_samples_per_second": 909.286, | |
| "eval_steps_per_second": 56.83, | |
| "step": 232000 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 3.69e-07, | |
| "loss": 2.092, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "eval_loss": 1.975371241569519, | |
| "eval_runtime": 110.1949, | |
| "eval_samples_per_second": 907.483, | |
| "eval_steps_per_second": 56.718, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "eval_loss": 1.9793789386749268, | |
| "eval_runtime": 109.4532, | |
| "eval_samples_per_second": 913.632, | |
| "eval_steps_per_second": 57.102, | |
| "step": 248000 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 3.6626666666666664e-07, | |
| "loss": 2.0968, | |
| "step": 256000 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "eval_loss": 1.9674972295761108, | |
| "eval_runtime": 110.2227, | |
| "eval_samples_per_second": 907.254, | |
| "eval_steps_per_second": 56.703, | |
| "step": 256000 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "eval_loss": 1.9709570407867432, | |
| "eval_runtime": 109.7565, | |
| "eval_samples_per_second": 911.108, | |
| "eval_steps_per_second": 56.944, | |
| "step": 264000 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 3.6353333333333335e-07, | |
| "loss": 2.0942, | |
| "step": 272000 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "eval_loss": 1.9712343215942383, | |
| "eval_runtime": 110.5189, | |
| "eval_samples_per_second": 904.823, | |
| "eval_steps_per_second": 56.551, | |
| "step": 272000 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "eval_loss": 1.966220736503601, | |
| "eval_runtime": 109.6691, | |
| "eval_samples_per_second": 911.834, | |
| "eval_steps_per_second": 56.99, | |
| "step": 280000 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 3.608e-07, | |
| "loss": 2.0929, | |
| "step": 288000 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "eval_loss": 1.9672335386276245, | |
| "eval_runtime": 110.4084, | |
| "eval_samples_per_second": 905.728, | |
| "eval_steps_per_second": 56.608, | |
| "step": 288000 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "eval_loss": 1.982972502708435, | |
| "eval_runtime": 110.1708, | |
| "eval_samples_per_second": 907.681, | |
| "eval_steps_per_second": 56.73, | |
| "step": 296000 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 3.5806666666666666e-07, | |
| "loss": 2.092, | |
| "step": 304000 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_loss": 1.9803731441497803, | |
| "eval_runtime": 109.6593, | |
| "eval_samples_per_second": 911.915, | |
| "eval_steps_per_second": 56.995, | |
| "step": 304000 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "eval_loss": 1.966055989265442, | |
| "eval_runtime": 111.5079, | |
| "eval_samples_per_second": 896.797, | |
| "eval_steps_per_second": 56.05, | |
| "step": 312000 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 3.553333333333333e-07, | |
| "loss": 2.0886, | |
| "step": 320000 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "eval_loss": 1.9667844772338867, | |
| "eval_runtime": 110.7165, | |
| "eval_samples_per_second": 903.208, | |
| "eval_steps_per_second": 56.451, | |
| "step": 320000 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_loss": 1.964282512664795, | |
| "eval_runtime": 110.4524, | |
| "eval_samples_per_second": 905.367, | |
| "eval_steps_per_second": 56.585, | |
| "step": 328000 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 3.5259999999999997e-07, | |
| "loss": 2.0883, | |
| "step": 336000 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "eval_loss": 1.971015214920044, | |
| "eval_runtime": 110.4534, | |
| "eval_samples_per_second": 905.359, | |
| "eval_steps_per_second": 56.585, | |
| "step": 336000 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "eval_loss": 1.9678236246109009, | |
| "eval_runtime": 110.0272, | |
| "eval_samples_per_second": 908.866, | |
| "eval_steps_per_second": 56.804, | |
| "step": 344000 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 3.498666666666667e-07, | |
| "loss": 2.0937, | |
| "step": 352000 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_loss": 1.9737088680267334, | |
| "eval_runtime": 110.4599, | |
| "eval_samples_per_second": 905.306, | |
| "eval_steps_per_second": 56.582, | |
| "step": 352000 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "eval_loss": 1.9638490676879883, | |
| "eval_runtime": 109.68, | |
| "eval_samples_per_second": 911.743, | |
| "eval_steps_per_second": 56.984, | |
| "step": 360000 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 3.4713333333333333e-07, | |
| "loss": 2.0899, | |
| "step": 368000 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "eval_loss": 1.9598619937896729, | |
| "eval_runtime": 110.8301, | |
| "eval_samples_per_second": 902.282, | |
| "eval_steps_per_second": 56.393, | |
| "step": 368000 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "eval_loss": 1.9570248126983643, | |
| "eval_runtime": 109.9153, | |
| "eval_samples_per_second": 909.792, | |
| "eval_steps_per_second": 56.862, | |
| "step": 376000 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 3.444e-07, | |
| "loss": 2.0839, | |
| "step": 384000 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "eval_loss": 1.9688061475753784, | |
| "eval_runtime": 110.0398, | |
| "eval_samples_per_second": 908.762, | |
| "eval_steps_per_second": 56.798, | |
| "step": 384000 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "eval_loss": 1.961317777633667, | |
| "eval_runtime": 110.3425, | |
| "eval_samples_per_second": 906.27, | |
| "eval_steps_per_second": 56.642, | |
| "step": 392000 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 3.416666666666667e-07, | |
| "loss": 2.0862, | |
| "step": 400000 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "eval_loss": 1.9686087369918823, | |
| "eval_runtime": 109.8056, | |
| "eval_samples_per_second": 910.7, | |
| "eval_steps_per_second": 56.919, | |
| "step": 400000 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "eval_loss": 1.969017505645752, | |
| "eval_runtime": 110.4224, | |
| "eval_samples_per_second": 905.613, | |
| "eval_steps_per_second": 56.601, | |
| "step": 408000 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 3.3893333333333335e-07, | |
| "loss": 2.0844, | |
| "step": 416000 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "eval_loss": 1.9665478467941284, | |
| "eval_runtime": 109.7701, | |
| "eval_samples_per_second": 910.995, | |
| "eval_steps_per_second": 56.937, | |
| "step": 416000 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "eval_loss": 1.9512009620666504, | |
| "eval_runtime": 110.6785, | |
| "eval_samples_per_second": 903.518, | |
| "eval_steps_per_second": 56.47, | |
| "step": 424000 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 3.3619999999999995e-07, | |
| "loss": 2.0802, | |
| "step": 432000 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "eval_loss": 1.965216040611267, | |
| "eval_runtime": 109.9673, | |
| "eval_samples_per_second": 909.361, | |
| "eval_steps_per_second": 56.835, | |
| "step": 432000 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "eval_loss": 1.959397315979004, | |
| "eval_runtime": 110.3077, | |
| "eval_samples_per_second": 906.555, | |
| "eval_steps_per_second": 56.66, | |
| "step": 440000 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 3.3346666666666666e-07, | |
| "loss": 2.0882, | |
| "step": 448000 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "eval_loss": 1.9543430805206299, | |
| "eval_runtime": 111.4673, | |
| "eval_samples_per_second": 897.124, | |
| "eval_steps_per_second": 56.07, | |
| "step": 448000 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "eval_loss": 1.9634778499603271, | |
| "eval_runtime": 111.4044, | |
| "eval_samples_per_second": 897.631, | |
| "eval_steps_per_second": 56.102, | |
| "step": 456000 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 3.307333333333333e-07, | |
| "loss": 2.0794, | |
| "step": 464000 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "eval_loss": 1.961761713027954, | |
| "eval_runtime": 110.0339, | |
| "eval_samples_per_second": 908.81, | |
| "eval_steps_per_second": 56.801, | |
| "step": 464000 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "eval_loss": 1.9616820812225342, | |
| "eval_runtime": 111.4358, | |
| "eval_samples_per_second": 897.378, | |
| "eval_steps_per_second": 56.086, | |
| "step": 472000 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 3.28e-07, | |
| "loss": 2.0848, | |
| "step": 480000 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "eval_loss": 1.9596595764160156, | |
| "eval_runtime": 109.7288, | |
| "eval_samples_per_second": 911.338, | |
| "eval_steps_per_second": 56.959, | |
| "step": 480000 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "eval_loss": 1.9585806131362915, | |
| "eval_runtime": 110.7191, | |
| "eval_samples_per_second": 903.187, | |
| "eval_steps_per_second": 56.449, | |
| "step": 488000 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 3.252666666666667e-07, | |
| "loss": 2.0814, | |
| "step": 496000 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "eval_loss": 1.9587445259094238, | |
| "eval_runtime": 110.1878, | |
| "eval_samples_per_second": 907.541, | |
| "eval_steps_per_second": 56.721, | |
| "step": 496000 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "eval_loss": 1.951024055480957, | |
| "eval_runtime": 111.6076, | |
| "eval_samples_per_second": 895.996, | |
| "eval_steps_per_second": 56.0, | |
| "step": 504000 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 3.2253333333333334e-07, | |
| "loss": 2.0765, | |
| "step": 512000 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "eval_loss": 1.9643146991729736, | |
| "eval_runtime": 110.4319, | |
| "eval_samples_per_second": 905.535, | |
| "eval_steps_per_second": 56.596, | |
| "step": 512000 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "eval_loss": 1.9586251974105835, | |
| "eval_runtime": 111.9851, | |
| "eval_samples_per_second": 892.976, | |
| "eval_steps_per_second": 55.811, | |
| "step": 520000 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 3.198e-07, | |
| "loss": 2.0887, | |
| "step": 528000 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "eval_loss": 1.9476207494735718, | |
| "eval_runtime": 111.761, | |
| "eval_samples_per_second": 894.766, | |
| "eval_steps_per_second": 55.923, | |
| "step": 528000 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "eval_loss": 1.9539178609848022, | |
| "eval_runtime": 112.4824, | |
| "eval_samples_per_second": 889.028, | |
| "eval_steps_per_second": 55.564, | |
| "step": 536000 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 3.1706666666666665e-07, | |
| "loss": 2.0857, | |
| "step": 544000 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "eval_loss": 1.9538391828536987, | |
| "eval_runtime": 110.284, | |
| "eval_samples_per_second": 906.75, | |
| "eval_steps_per_second": 56.672, | |
| "step": 544000 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "eval_loss": 1.9528268575668335, | |
| "eval_runtime": 110.3047, | |
| "eval_samples_per_second": 906.58, | |
| "eval_steps_per_second": 56.661, | |
| "step": 552000 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 3.1433333333333336e-07, | |
| "loss": 2.0798, | |
| "step": 560000 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "eval_loss": 1.958569049835205, | |
| "eval_runtime": 110.3087, | |
| "eval_samples_per_second": 906.547, | |
| "eval_steps_per_second": 56.659, | |
| "step": 560000 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "eval_loss": 1.966043472290039, | |
| "eval_runtime": 110.287, | |
| "eval_samples_per_second": 906.725, | |
| "eval_steps_per_second": 56.67, | |
| "step": 568000 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 3.116e-07, | |
| "loss": 2.0752, | |
| "step": 576000 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "eval_loss": 1.9638713598251343, | |
| "eval_runtime": 110.4682, | |
| "eval_samples_per_second": 905.238, | |
| "eval_steps_per_second": 56.577, | |
| "step": 576000 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "eval_loss": 1.950478434562683, | |
| "eval_runtime": 112.4819, | |
| "eval_samples_per_second": 889.032, | |
| "eval_steps_per_second": 55.565, | |
| "step": 584000 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "learning_rate": 3.0886666666666667e-07, | |
| "loss": 2.0771, | |
| "step": 592000 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_loss": 1.9551353454589844, | |
| "eval_runtime": 111.1621, | |
| "eval_samples_per_second": 899.587, | |
| "eval_steps_per_second": 56.224, | |
| "step": 592000 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "eval_loss": 1.9495452642440796, | |
| "eval_runtime": 110.1306, | |
| "eval_samples_per_second": 908.013, | |
| "eval_steps_per_second": 56.751, | |
| "step": 600000 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 3.061333333333333e-07, | |
| "loss": 2.0772, | |
| "step": 608000 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "eval_loss": 1.9536247253417969, | |
| "eval_runtime": 110.5342, | |
| "eval_samples_per_second": 904.697, | |
| "eval_steps_per_second": 56.544, | |
| "step": 608000 | |
| }, | |
| { | |
| "epoch": 5.19, | |
| "eval_loss": 1.9566668272018433, | |
| "eval_runtime": 110.8939, | |
| "eval_samples_per_second": 901.763, | |
| "eval_steps_per_second": 56.36, | |
| "step": 616000 | |
| }, | |
| { | |
| "epoch": 5.25, | |
| "learning_rate": 3.034e-07, | |
| "loss": 2.0836, | |
| "step": 624000 | |
| }, | |
| { | |
| "epoch": 5.25, | |
| "eval_loss": 1.9533698558807373, | |
| "eval_runtime": 111.153, | |
| "eval_samples_per_second": 899.661, | |
| "eval_steps_per_second": 56.229, | |
| "step": 624000 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "eval_loss": 1.9663032293319702, | |
| "eval_runtime": 113.3189, | |
| "eval_samples_per_second": 882.465, | |
| "eval_steps_per_second": 55.154, | |
| "step": 632000 | |
| }, | |
| { | |
| "epoch": 5.39, | |
| "learning_rate": 3.0066666666666663e-07, | |
| "loss": 2.0851, | |
| "step": 640000 | |
| }, | |
| { | |
| "epoch": 5.39, | |
| "eval_loss": 1.9535197019577026, | |
| "eval_runtime": 110.5244, | |
| "eval_samples_per_second": 904.778, | |
| "eval_steps_per_second": 56.549, | |
| "step": 640000 | |
| }, | |
| { | |
| "epoch": 5.46, | |
| "eval_loss": 1.9554091691970825, | |
| "eval_runtime": 111.1979, | |
| "eval_samples_per_second": 899.298, | |
| "eval_steps_per_second": 56.206, | |
| "step": 648000 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "learning_rate": 2.9793333333333334e-07, | |
| "loss": 2.0842, | |
| "step": 656000 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "eval_loss": 1.9539320468902588, | |
| "eval_runtime": 110.1114, | |
| "eval_samples_per_second": 908.171, | |
| "eval_steps_per_second": 56.761, | |
| "step": 656000 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "eval_loss": 1.9588661193847656, | |
| "eval_runtime": 110.2861, | |
| "eval_samples_per_second": 906.732, | |
| "eval_steps_per_second": 56.671, | |
| "step": 664000 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "learning_rate": 2.952e-07, | |
| "loss": 2.088, | |
| "step": 672000 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "eval_loss": 1.9571921825408936, | |
| "eval_runtime": 110.8703, | |
| "eval_samples_per_second": 901.955, | |
| "eval_steps_per_second": 56.372, | |
| "step": 672000 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "eval_loss": 1.9603205919265747, | |
| "eval_runtime": 111.1855, | |
| "eval_samples_per_second": 899.397, | |
| "eval_steps_per_second": 56.212, | |
| "step": 680000 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "learning_rate": 2.9246666666666665e-07, | |
| "loss": 2.075, | |
| "step": 688000 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "eval_loss": 1.9638681411743164, | |
| "eval_runtime": 110.5603, | |
| "eval_samples_per_second": 904.483, | |
| "eval_steps_per_second": 56.53, | |
| "step": 688000 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "eval_loss": 1.9536782503128052, | |
| "eval_runtime": 111.9104, | |
| "eval_samples_per_second": 893.572, | |
| "eval_steps_per_second": 55.848, | |
| "step": 696000 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 2.897333333333333e-07, | |
| "loss": 2.077, | |
| "step": 704000 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "eval_loss": 1.961190104484558, | |
| "eval_runtime": 110.2085, | |
| "eval_samples_per_second": 907.371, | |
| "eval_steps_per_second": 56.711, | |
| "step": 704000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.9571187496185303, | |
| "eval_runtime": 111.1, | |
| "eval_samples_per_second": 900.09, | |
| "eval_steps_per_second": 56.256, | |
| "step": 712000 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "learning_rate": 2.8699999999999996e-07, | |
| "loss": 2.0692, | |
| "step": 720000 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "eval_loss": 1.954491376876831, | |
| "eval_runtime": 110.3925, | |
| "eval_samples_per_second": 905.858, | |
| "eval_steps_per_second": 56.616, | |
| "step": 720000 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "eval_loss": 1.9494022130966187, | |
| "eval_runtime": 111.0587, | |
| "eval_samples_per_second": 900.425, | |
| "eval_steps_per_second": 56.277, | |
| "step": 728000 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "learning_rate": 2.8426666666666667e-07, | |
| "loss": 2.087, | |
| "step": 736000 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "eval_loss": 1.9555366039276123, | |
| "eval_runtime": 111.4849, | |
| "eval_samples_per_second": 896.982, | |
| "eval_steps_per_second": 56.061, | |
| "step": 736000 | |
| }, | |
| { | |
| "epoch": 6.27, | |
| "eval_loss": 1.9565927982330322, | |
| "eval_runtime": 110.3868, | |
| "eval_samples_per_second": 905.905, | |
| "eval_steps_per_second": 56.619, | |
| "step": 744000 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 2.815333333333333e-07, | |
| "loss": 2.0783, | |
| "step": 752000 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "eval_loss": 1.944687843322754, | |
| "eval_runtime": 110.7554, | |
| "eval_samples_per_second": 902.891, | |
| "eval_steps_per_second": 56.431, | |
| "step": 752000 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "eval_loss": 1.9517587423324585, | |
| "eval_runtime": 110.834, | |
| "eval_samples_per_second": 902.25, | |
| "eval_steps_per_second": 56.391, | |
| "step": 760000 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "learning_rate": 2.7880000000000003e-07, | |
| "loss": 2.0771, | |
| "step": 768000 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "eval_loss": 1.942885160446167, | |
| "eval_runtime": 111.4733, | |
| "eval_samples_per_second": 897.076, | |
| "eval_steps_per_second": 56.067, | |
| "step": 768000 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "eval_loss": 1.9603298902511597, | |
| "eval_runtime": 110.8474, | |
| "eval_samples_per_second": 902.141, | |
| "eval_steps_per_second": 56.384, | |
| "step": 776000 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "learning_rate": 2.7606666666666664e-07, | |
| "loss": 2.0794, | |
| "step": 784000 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "eval_loss": 1.9503004550933838, | |
| "eval_runtime": 110.8398, | |
| "eval_samples_per_second": 902.203, | |
| "eval_steps_per_second": 56.388, | |
| "step": 784000 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "eval_loss": 1.9571810960769653, | |
| "eval_runtime": 110.2885, | |
| "eval_samples_per_second": 906.713, | |
| "eval_steps_per_second": 56.67, | |
| "step": 792000 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "learning_rate": 2.733333333333333e-07, | |
| "loss": 2.0777, | |
| "step": 800000 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "eval_loss": 1.9606574773788452, | |
| "eval_runtime": 110.4898, | |
| "eval_samples_per_second": 905.061, | |
| "eval_steps_per_second": 56.566, | |
| "step": 800000 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "eval_loss": 1.952511191368103, | |
| "eval_runtime": 111.2869, | |
| "eval_samples_per_second": 898.579, | |
| "eval_steps_per_second": 56.161, | |
| "step": 808000 | |
| }, | |
| { | |
| "epoch": 6.87, | |
| "learning_rate": 2.706e-07, | |
| "loss": 2.0725, | |
| "step": 816000 | |
| }, | |
| { | |
| "epoch": 6.87, | |
| "eval_loss": 1.9495289325714111, | |
| "eval_runtime": 111.2387, | |
| "eval_samples_per_second": 898.968, | |
| "eval_steps_per_second": 56.185, | |
| "step": 816000 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "eval_loss": 1.9516665935516357, | |
| "eval_runtime": 111.2649, | |
| "eval_samples_per_second": 898.756, | |
| "eval_steps_per_second": 56.172, | |
| "step": 824000 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 2.6786666666666666e-07, | |
| "loss": 2.0863, | |
| "step": 832000 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "eval_loss": 1.9522712230682373, | |
| "eval_runtime": 110.9997, | |
| "eval_samples_per_second": 900.903, | |
| "eval_steps_per_second": 56.306, | |
| "step": 832000 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "eval_loss": 1.944066047668457, | |
| "eval_runtime": 110.9939, | |
| "eval_samples_per_second": 900.95, | |
| "eval_steps_per_second": 56.309, | |
| "step": 840000 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 2.651333333333333e-07, | |
| "loss": 2.0735, | |
| "step": 848000 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "eval_loss": 1.942973256111145, | |
| "eval_runtime": 110.4043, | |
| "eval_samples_per_second": 905.762, | |
| "eval_steps_per_second": 56.61, | |
| "step": 848000 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "eval_loss": 1.9516521692276, | |
| "eval_runtime": 110.9458, | |
| "eval_samples_per_second": 901.341, | |
| "eval_steps_per_second": 56.334, | |
| "step": 856000 | |
| }, | |
| { | |
| "epoch": 7.28, | |
| "learning_rate": 2.624e-07, | |
| "loss": 2.0808, | |
| "step": 864000 | |
| }, | |
| { | |
| "epoch": 7.28, | |
| "eval_loss": 1.9442354440689087, | |
| "eval_runtime": 110.9964, | |
| "eval_samples_per_second": 900.93, | |
| "eval_steps_per_second": 56.308, | |
| "step": 864000 | |
| }, | |
| { | |
| "epoch": 7.34, | |
| "eval_loss": 1.9414219856262207, | |
| "eval_runtime": 111.0475, | |
| "eval_samples_per_second": 900.515, | |
| "eval_steps_per_second": 56.282, | |
| "step": 872000 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "learning_rate": 2.596666666666667e-07, | |
| "loss": 2.0756, | |
| "step": 880000 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "eval_loss": 1.943913459777832, | |
| "eval_runtime": 110.5804, | |
| "eval_samples_per_second": 904.319, | |
| "eval_steps_per_second": 56.52, | |
| "step": 880000 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "eval_loss": 1.9428108930587769, | |
| "eval_runtime": 110.7686, | |
| "eval_samples_per_second": 902.783, | |
| "eval_steps_per_second": 56.424, | |
| "step": 888000 | |
| }, | |
| { | |
| "epoch": 7.55, | |
| "learning_rate": 2.5693333333333333e-07, | |
| "loss": 2.0799, | |
| "step": 896000 | |
| }, | |
| { | |
| "epoch": 7.55, | |
| "eval_loss": 1.9471795558929443, | |
| "eval_runtime": 110.5526, | |
| "eval_samples_per_second": 904.547, | |
| "eval_steps_per_second": 56.534, | |
| "step": 896000 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "eval_loss": 1.9425973892211914, | |
| "eval_runtime": 110.4745, | |
| "eval_samples_per_second": 905.186, | |
| "eval_steps_per_second": 56.574, | |
| "step": 904000 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 2.542e-07, | |
| "loss": 2.0717, | |
| "step": 912000 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "eval_loss": 1.9460599422454834, | |
| "eval_runtime": 110.5105, | |
| "eval_samples_per_second": 904.891, | |
| "eval_steps_per_second": 56.556, | |
| "step": 912000 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "eval_loss": 1.958345651626587, | |
| "eval_runtime": 110.4629, | |
| "eval_samples_per_second": 905.281, | |
| "eval_steps_per_second": 56.58, | |
| "step": 920000 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "learning_rate": 2.5146666666666664e-07, | |
| "loss": 2.0799, | |
| "step": 928000 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "eval_loss": 1.9433069229125977, | |
| "eval_runtime": 111.4685, | |
| "eval_samples_per_second": 897.115, | |
| "eval_steps_per_second": 56.07, | |
| "step": 928000 | |
| }, | |
| { | |
| "epoch": 7.88, | |
| "eval_loss": 1.9442389011383057, | |
| "eval_runtime": 110.6773, | |
| "eval_samples_per_second": 903.528, | |
| "eval_steps_per_second": 56.47, | |
| "step": 936000 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "learning_rate": 2.4873333333333335e-07, | |
| "loss": 2.0704, | |
| "step": 944000 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "eval_loss": 1.939575433731079, | |
| "eval_runtime": 110.5017, | |
| "eval_samples_per_second": 904.964, | |
| "eval_steps_per_second": 56.56, | |
| "step": 944000 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "eval_loss": 1.9409291744232178, | |
| "eval_runtime": 110.9407, | |
| "eval_samples_per_second": 901.383, | |
| "eval_steps_per_second": 56.336, | |
| "step": 952000 | |
| }, | |
| { | |
| "epoch": 8.08, | |
| "learning_rate": 2.46e-07, | |
| "loss": 2.0785, | |
| "step": 960000 | |
| }, | |
| { | |
| "epoch": 8.08, | |
| "eval_loss": 1.9520161151885986, | |
| "eval_runtime": 110.8429, | |
| "eval_samples_per_second": 902.178, | |
| "eval_steps_per_second": 56.386, | |
| "step": 960000 | |
| }, | |
| { | |
| "epoch": 8.15, | |
| "eval_loss": 1.9408738613128662, | |
| "eval_runtime": 111.2876, | |
| "eval_samples_per_second": 898.572, | |
| "eval_steps_per_second": 56.161, | |
| "step": 968000 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "learning_rate": 2.4326666666666666e-07, | |
| "loss": 2.0761, | |
| "step": 976000 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "eval_loss": 1.9469316005706787, | |
| "eval_runtime": 111.4838, | |
| "eval_samples_per_second": 896.991, | |
| "eval_steps_per_second": 56.062, | |
| "step": 976000 | |
| }, | |
| { | |
| "epoch": 8.29, | |
| "eval_loss": 1.937188744544983, | |
| "eval_runtime": 110.6386, | |
| "eval_samples_per_second": 903.843, | |
| "eval_steps_per_second": 56.49, | |
| "step": 984000 | |
| }, | |
| { | |
| "epoch": 8.35, | |
| "learning_rate": 2.405333333333333e-07, | |
| "loss": 2.0739, | |
| "step": 992000 | |
| }, | |
| { | |
| "epoch": 8.35, | |
| "eval_loss": 1.938472867012024, | |
| "eval_runtime": 110.7286, | |
| "eval_samples_per_second": 903.109, | |
| "eval_steps_per_second": 56.444, | |
| "step": 992000 | |
| }, | |
| { | |
| "epoch": 8.42, | |
| "eval_loss": 1.953993320465088, | |
| "eval_runtime": 111.1301, | |
| "eval_samples_per_second": 899.846, | |
| "eval_steps_per_second": 56.24, | |
| "step": 1000000 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "learning_rate": 2.3779999999999997e-07, | |
| "loss": 2.0761, | |
| "step": 1008000 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "eval_loss": 1.9488329887390137, | |
| "eval_runtime": 110.8551, | |
| "eval_samples_per_second": 902.079, | |
| "eval_steps_per_second": 56.38, | |
| "step": 1008000 | |
| }, | |
| { | |
| "epoch": 8.56, | |
| "eval_loss": 1.946441888809204, | |
| "eval_runtime": 110.9628, | |
| "eval_samples_per_second": 901.203, | |
| "eval_steps_per_second": 56.325, | |
| "step": 1016000 | |
| }, | |
| { | |
| "epoch": 8.62, | |
| "learning_rate": 2.3506666666666668e-07, | |
| "loss": 2.0725, | |
| "step": 1024000 | |
| }, | |
| { | |
| "epoch": 8.62, | |
| "eval_loss": 1.9465641975402832, | |
| "eval_runtime": 111.87, | |
| "eval_samples_per_second": 893.895, | |
| "eval_steps_per_second": 55.868, | |
| "step": 1024000 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "eval_loss": 1.9460062980651855, | |
| "eval_runtime": 111.2897, | |
| "eval_samples_per_second": 898.556, | |
| "eval_steps_per_second": 56.16, | |
| "step": 1032000 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "learning_rate": 2.3233333333333334e-07, | |
| "loss": 2.0704, | |
| "step": 1040000 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "eval_loss": 1.9449492692947388, | |
| "eval_runtime": 111.0347, | |
| "eval_samples_per_second": 900.62, | |
| "eval_steps_per_second": 56.289, | |
| "step": 1040000 | |
| }, | |
| { | |
| "epoch": 8.83, | |
| "eval_loss": 1.9492580890655518, | |
| "eval_runtime": 111.2543, | |
| "eval_samples_per_second": 898.842, | |
| "eval_steps_per_second": 56.178, | |
| "step": 1048000 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "learning_rate": 2.2960000000000002e-07, | |
| "loss": 2.0734, | |
| "step": 1056000 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "eval_loss": 1.946271300315857, | |
| "eval_runtime": 111.7276, | |
| "eval_samples_per_second": 895.034, | |
| "eval_steps_per_second": 55.94, | |
| "step": 1056000 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "eval_loss": 1.9402709007263184, | |
| "eval_runtime": 111.4255, | |
| "eval_samples_per_second": 897.46, | |
| "eval_steps_per_second": 56.091, | |
| "step": 1064000 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 2.2686666666666667e-07, | |
| "loss": 2.0744, | |
| "step": 1072000 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "eval_loss": 1.9467432498931885, | |
| "eval_runtime": 110.7175, | |
| "eval_samples_per_second": 903.2, | |
| "eval_steps_per_second": 56.45, | |
| "step": 1072000 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "eval_loss": 1.9405895471572876, | |
| "eval_runtime": 111.339, | |
| "eval_samples_per_second": 898.158, | |
| "eval_steps_per_second": 56.135, | |
| "step": 1080000 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "learning_rate": 2.2413333333333333e-07, | |
| "loss": 2.0776, | |
| "step": 1088000 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "eval_loss": 1.9491678476333618, | |
| "eval_runtime": 112.0203, | |
| "eval_samples_per_second": 892.696, | |
| "eval_steps_per_second": 55.793, | |
| "step": 1088000 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "eval_loss": 1.9432501792907715, | |
| "eval_runtime": 111.5552, | |
| "eval_samples_per_second": 896.417, | |
| "eval_steps_per_second": 56.026, | |
| "step": 1096000 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "learning_rate": 2.214e-07, | |
| "loss": 2.068, | |
| "step": 1104000 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "eval_loss": 1.9449836015701294, | |
| "eval_runtime": 111.8965, | |
| "eval_samples_per_second": 893.683, | |
| "eval_steps_per_second": 55.855, | |
| "step": 1104000 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "eval_loss": 1.9473295211791992, | |
| "eval_runtime": 111.6609, | |
| "eval_samples_per_second": 895.569, | |
| "eval_steps_per_second": 55.973, | |
| "step": 1112000 | |
| }, | |
| { | |
| "epoch": 9.43, | |
| "learning_rate": 2.1866666666666667e-07, | |
| "loss": 2.0755, | |
| "step": 1120000 | |
| }, | |
| { | |
| "epoch": 9.43, | |
| "eval_loss": 1.9459151029586792, | |
| "eval_runtime": 111.1268, | |
| "eval_samples_per_second": 899.873, | |
| "eval_steps_per_second": 56.242, | |
| "step": 1120000 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "eval_loss": 1.9562652111053467, | |
| "eval_runtime": 110.7077, | |
| "eval_samples_per_second": 903.279, | |
| "eval_steps_per_second": 56.455, | |
| "step": 1128000 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "learning_rate": 2.1593333333333332e-07, | |
| "loss": 2.0783, | |
| "step": 1136000 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "eval_loss": 1.936863899230957, | |
| "eval_runtime": 110.9141, | |
| "eval_samples_per_second": 901.599, | |
| "eval_steps_per_second": 56.35, | |
| "step": 1136000 | |
| }, | |
| { | |
| "epoch": 9.63, | |
| "eval_loss": 1.9461090564727783, | |
| "eval_runtime": 110.7314, | |
| "eval_samples_per_second": 903.086, | |
| "eval_steps_per_second": 56.443, | |
| "step": 1144000 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "learning_rate": 2.132e-07, | |
| "loss": 2.0776, | |
| "step": 1152000 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "eval_loss": 1.9494104385375977, | |
| "eval_runtime": 112.0046, | |
| "eval_samples_per_second": 892.82, | |
| "eval_steps_per_second": 55.801, | |
| "step": 1152000 | |
| }, | |
| { | |
| "epoch": 9.77, | |
| "eval_loss": 1.9312143325805664, | |
| "eval_runtime": 111.1816, | |
| "eval_samples_per_second": 899.429, | |
| "eval_steps_per_second": 56.214, | |
| "step": 1160000 | |
| }, | |
| { | |
| "epoch": 9.84, | |
| "learning_rate": 2.1046666666666666e-07, | |
| "loss": 2.0757, | |
| "step": 1168000 | |
| }, | |
| { | |
| "epoch": 9.84, | |
| "eval_loss": 1.9451590776443481, | |
| "eval_runtime": 111.0971, | |
| "eval_samples_per_second": 900.114, | |
| "eval_steps_per_second": 56.257, | |
| "step": 1168000 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "eval_loss": 1.9424793720245361, | |
| "eval_runtime": 112.0686, | |
| "eval_samples_per_second": 892.31, | |
| "eval_steps_per_second": 55.769, | |
| "step": 1176000 | |
| }, | |
| { | |
| "epoch": 9.97, | |
| "learning_rate": 2.0773333333333334e-07, | |
| "loss": 2.0776, | |
| "step": 1184000 | |
| }, | |
| { | |
| "epoch": 9.97, | |
| "eval_loss": 1.9535951614379883, | |
| "eval_runtime": 112.2353, | |
| "eval_samples_per_second": 890.986, | |
| "eval_steps_per_second": 55.687, | |
| "step": 1184000 | |
| }, | |
| { | |
| "epoch": 10.04, | |
| "eval_loss": 1.93512761592865, | |
| "eval_runtime": 111.2352, | |
| "eval_samples_per_second": 898.996, | |
| "eval_steps_per_second": 56.187, | |
| "step": 1192000 | |
| }, | |
| { | |
| "epoch": 10.11, | |
| "learning_rate": 2.05e-07, | |
| "loss": 2.0769, | |
| "step": 1200000 | |
| }, | |
| { | |
| "epoch": 10.11, | |
| "eval_loss": 1.930122971534729, | |
| "eval_runtime": 111.6202, | |
| "eval_samples_per_second": 895.896, | |
| "eval_steps_per_second": 55.993, | |
| "step": 1200000 | |
| }, | |
| { | |
| "epoch": 10.17, | |
| "eval_loss": 1.9463820457458496, | |
| "eval_runtime": 110.7887, | |
| "eval_samples_per_second": 902.619, | |
| "eval_steps_per_second": 56.414, | |
| "step": 1208000 | |
| }, | |
| { | |
| "epoch": 10.24, | |
| "learning_rate": 2.0226666666666668e-07, | |
| "loss": 2.071, | |
| "step": 1216000 | |
| }, | |
| { | |
| "epoch": 10.24, | |
| "eval_loss": 1.9409968852996826, | |
| "eval_runtime": 111.4322, | |
| "eval_samples_per_second": 897.406, | |
| "eval_steps_per_second": 56.088, | |
| "step": 1216000 | |
| }, | |
| { | |
| "epoch": 10.31, | |
| "eval_loss": 1.9320902824401855, | |
| "eval_runtime": 111.6751, | |
| "eval_samples_per_second": 895.455, | |
| "eval_steps_per_second": 55.966, | |
| "step": 1224000 | |
| }, | |
| { | |
| "epoch": 10.37, | |
| "learning_rate": 1.9953333333333333e-07, | |
| "loss": 2.0702, | |
| "step": 1232000 | |
| }, | |
| { | |
| "epoch": 10.37, | |
| "eval_loss": 1.9406121969223022, | |
| "eval_runtime": 111.9712, | |
| "eval_samples_per_second": 893.086, | |
| "eval_steps_per_second": 55.818, | |
| "step": 1232000 | |
| }, | |
| { | |
| "epoch": 10.44, | |
| "eval_loss": 1.9524641036987305, | |
| "eval_runtime": 111.105, | |
| "eval_samples_per_second": 900.05, | |
| "eval_steps_per_second": 56.253, | |
| "step": 1240000 | |
| }, | |
| { | |
| "epoch": 10.51, | |
| "learning_rate": 1.968e-07, | |
| "loss": 2.0716, | |
| "step": 1248000 | |
| }, | |
| { | |
| "epoch": 10.51, | |
| "eval_loss": 1.9418323040008545, | |
| "eval_runtime": 110.5724, | |
| "eval_samples_per_second": 904.385, | |
| "eval_steps_per_second": 56.524, | |
| "step": 1248000 | |
| }, | |
| { | |
| "epoch": 10.58, | |
| "eval_loss": 1.9372801780700684, | |
| "eval_runtime": 111.126, | |
| "eval_samples_per_second": 899.88, | |
| "eval_steps_per_second": 56.242, | |
| "step": 1256000 | |
| }, | |
| { | |
| "epoch": 10.64, | |
| "learning_rate": 1.9406666666666667e-07, | |
| "loss": 2.0753, | |
| "step": 1264000 | |
| }, | |
| { | |
| "epoch": 10.64, | |
| "eval_loss": 1.9362831115722656, | |
| "eval_runtime": 111.0107, | |
| "eval_samples_per_second": 900.814, | |
| "eval_steps_per_second": 56.301, | |
| "step": 1264000 | |
| }, | |
| { | |
| "epoch": 10.71, | |
| "eval_loss": 1.950430989265442, | |
| "eval_runtime": 111.42, | |
| "eval_samples_per_second": 897.505, | |
| "eval_steps_per_second": 56.094, | |
| "step": 1272000 | |
| }, | |
| { | |
| "epoch": 10.78, | |
| "learning_rate": 1.9133333333333333e-07, | |
| "loss": 2.0757, | |
| "step": 1280000 | |
| }, | |
| { | |
| "epoch": 10.78, | |
| "eval_loss": 1.937592625617981, | |
| "eval_runtime": 111.8154, | |
| "eval_samples_per_second": 894.331, | |
| "eval_steps_per_second": 55.896, | |
| "step": 1280000 | |
| }, | |
| { | |
| "epoch": 10.85, | |
| "eval_loss": 1.9350725412368774, | |
| "eval_runtime": 110.9987, | |
| "eval_samples_per_second": 900.912, | |
| "eval_steps_per_second": 56.307, | |
| "step": 1288000 | |
| }, | |
| { | |
| "epoch": 10.91, | |
| "learning_rate": 1.886e-07, | |
| "loss": 2.0656, | |
| "step": 1296000 | |
| }, | |
| { | |
| "epoch": 10.91, | |
| "eval_loss": 1.9444907903671265, | |
| "eval_runtime": 112.1206, | |
| "eval_samples_per_second": 891.897, | |
| "eval_steps_per_second": 55.744, | |
| "step": 1296000 | |
| }, | |
| { | |
| "epoch": 10.98, | |
| "eval_loss": 1.9282187223434448, | |
| "eval_runtime": 111.5472, | |
| "eval_samples_per_second": 896.482, | |
| "eval_steps_per_second": 56.03, | |
| "step": 1304000 | |
| }, | |
| { | |
| "epoch": 11.05, | |
| "learning_rate": 1.8586666666666666e-07, | |
| "loss": 2.0732, | |
| "step": 1312000 | |
| }, | |
| { | |
| "epoch": 11.05, | |
| "eval_loss": 1.9437243938446045, | |
| "eval_runtime": 111.1188, | |
| "eval_samples_per_second": 899.937, | |
| "eval_steps_per_second": 56.246, | |
| "step": 1312000 | |
| }, | |
| { | |
| "epoch": 11.12, | |
| "eval_loss": 1.9500561952590942, | |
| "eval_runtime": 112.2135, | |
| "eval_samples_per_second": 891.158, | |
| "eval_steps_per_second": 55.697, | |
| "step": 1320000 | |
| }, | |
| { | |
| "epoch": 11.18, | |
| "learning_rate": 1.8313333333333332e-07, | |
| "loss": 2.0756, | |
| "step": 1328000 | |
| }, | |
| { | |
| "epoch": 11.18, | |
| "eval_loss": 1.9378612041473389, | |
| "eval_runtime": 111.2719, | |
| "eval_samples_per_second": 898.699, | |
| "eval_steps_per_second": 56.169, | |
| "step": 1328000 | |
| }, | |
| { | |
| "epoch": 11.25, | |
| "eval_loss": 1.942953109741211, | |
| "eval_runtime": 111.8733, | |
| "eval_samples_per_second": 893.869, | |
| "eval_steps_per_second": 55.867, | |
| "step": 1336000 | |
| }, | |
| { | |
| "epoch": 11.32, | |
| "learning_rate": 1.804e-07, | |
| "loss": 2.0885, | |
| "step": 1344000 | |
| }, | |
| { | |
| "epoch": 11.32, | |
| "eval_loss": 1.9392478466033936, | |
| "eval_runtime": 111.6275, | |
| "eval_samples_per_second": 895.836, | |
| "eval_steps_per_second": 55.99, | |
| "step": 1344000 | |
| }, | |
| { | |
| "epoch": 11.39, | |
| "eval_loss": 1.9343684911727905, | |
| "eval_runtime": 110.9879, | |
| "eval_samples_per_second": 900.999, | |
| "eval_steps_per_second": 56.312, | |
| "step": 1352000 | |
| }, | |
| { | |
| "epoch": 11.45, | |
| "learning_rate": 1.7766666666666666e-07, | |
| "loss": 2.0758, | |
| "step": 1360000 | |
| }, | |
| { | |
| "epoch": 11.45, | |
| "eval_loss": 1.9363566637039185, | |
| "eval_runtime": 112.2823, | |
| "eval_samples_per_second": 890.612, | |
| "eval_steps_per_second": 55.663, | |
| "step": 1360000 | |
| }, | |
| { | |
| "epoch": 11.52, | |
| "eval_loss": 1.9404397010803223, | |
| "eval_runtime": 111.7313, | |
| "eval_samples_per_second": 895.004, | |
| "eval_steps_per_second": 55.938, | |
| "step": 1368000 | |
| }, | |
| { | |
| "epoch": 11.59, | |
| "learning_rate": 1.7493333333333334e-07, | |
| "loss": 2.0693, | |
| "step": 1376000 | |
| }, | |
| { | |
| "epoch": 11.59, | |
| "eval_loss": 1.9346548318862915, | |
| "eval_runtime": 112.1875, | |
| "eval_samples_per_second": 891.365, | |
| "eval_steps_per_second": 55.71, | |
| "step": 1376000 | |
| }, | |
| { | |
| "epoch": 11.65, | |
| "eval_loss": 1.9437816143035889, | |
| "eval_runtime": 110.9656, | |
| "eval_samples_per_second": 901.18, | |
| "eval_steps_per_second": 56.324, | |
| "step": 1384000 | |
| }, | |
| { | |
| "epoch": 11.72, | |
| "learning_rate": 1.722e-07, | |
| "loss": 2.0675, | |
| "step": 1392000 | |
| }, | |
| { | |
| "epoch": 11.72, | |
| "eval_loss": 1.936692476272583, | |
| "eval_runtime": 111.3228, | |
| "eval_samples_per_second": 898.289, | |
| "eval_steps_per_second": 56.143, | |
| "step": 1392000 | |
| }, | |
| { | |
| "epoch": 11.79, | |
| "eval_loss": 1.9438282251358032, | |
| "eval_runtime": 113.421, | |
| "eval_samples_per_second": 881.671, | |
| "eval_steps_per_second": 55.104, | |
| "step": 1400000 | |
| }, | |
| { | |
| "epoch": 11.86, | |
| "learning_rate": 1.6946666666666668e-07, | |
| "loss": 2.0731, | |
| "step": 1408000 | |
| }, | |
| { | |
| "epoch": 11.86, | |
| "eval_loss": 1.9327083826065063, | |
| "eval_runtime": 111.5562, | |
| "eval_samples_per_second": 896.409, | |
| "eval_steps_per_second": 56.026, | |
| "step": 1408000 | |
| }, | |
| { | |
| "epoch": 11.92, | |
| "eval_loss": 1.93413245677948, | |
| "eval_runtime": 111.6893, | |
| "eval_samples_per_second": 895.341, | |
| "eval_steps_per_second": 55.959, | |
| "step": 1416000 | |
| }, | |
| { | |
| "epoch": 11.99, | |
| "learning_rate": 1.6673333333333333e-07, | |
| "loss": 2.0774, | |
| "step": 1424000 | |
| }, | |
| { | |
| "epoch": 11.99, | |
| "eval_loss": 1.9390318393707275, | |
| "eval_runtime": 111.7654, | |
| "eval_samples_per_second": 894.732, | |
| "eval_steps_per_second": 55.921, | |
| "step": 1424000 | |
| }, | |
| { | |
| "epoch": 12.06, | |
| "eval_loss": 1.9456911087036133, | |
| "eval_runtime": 112.3213, | |
| "eval_samples_per_second": 890.303, | |
| "eval_steps_per_second": 55.644, | |
| "step": 1432000 | |
| }, | |
| { | |
| "epoch": 12.13, | |
| "learning_rate": 1.64e-07, | |
| "loss": 2.0738, | |
| "step": 1440000 | |
| }, | |
| { | |
| "epoch": 12.13, | |
| "eval_loss": 1.9436718225479126, | |
| "eval_runtime": 112.04, | |
| "eval_samples_per_second": 892.539, | |
| "eval_steps_per_second": 55.784, | |
| "step": 1440000 | |
| }, | |
| { | |
| "epoch": 12.19, | |
| "eval_loss": 1.9353281259536743, | |
| "eval_runtime": 111.1163, | |
| "eval_samples_per_second": 899.958, | |
| "eval_steps_per_second": 56.247, | |
| "step": 1448000 | |
| }, | |
| { | |
| "epoch": 12.26, | |
| "learning_rate": 1.6126666666666667e-07, | |
| "loss": 2.0667, | |
| "step": 1456000 | |
| }, | |
| { | |
| "epoch": 12.26, | |
| "eval_loss": 1.942425012588501, | |
| "eval_runtime": 112.2929, | |
| "eval_samples_per_second": 890.528, | |
| "eval_steps_per_second": 55.658, | |
| "step": 1456000 | |
| }, | |
| { | |
| "epoch": 12.33, | |
| "eval_loss": 1.9434609413146973, | |
| "eval_runtime": 111.3439, | |
| "eval_samples_per_second": 898.118, | |
| "eval_steps_per_second": 56.132, | |
| "step": 1464000 | |
| }, | |
| { | |
| "epoch": 12.4, | |
| "learning_rate": 1.5853333333333332e-07, | |
| "loss": 2.0674, | |
| "step": 1472000 | |
| }, | |
| { | |
| "epoch": 12.4, | |
| "eval_loss": 1.933566927909851, | |
| "eval_runtime": 112.0783, | |
| "eval_samples_per_second": 892.234, | |
| "eval_steps_per_second": 55.765, | |
| "step": 1472000 | |
| }, | |
| { | |
| "epoch": 12.46, | |
| "eval_loss": 1.9461445808410645, | |
| "eval_runtime": 111.6861, | |
| "eval_samples_per_second": 895.367, | |
| "eval_steps_per_second": 55.96, | |
| "step": 1480000 | |
| }, | |
| { | |
| "epoch": 12.53, | |
| "learning_rate": 1.558e-07, | |
| "loss": 2.0704, | |
| "step": 1488000 | |
| }, | |
| { | |
| "epoch": 12.53, | |
| "eval_loss": 1.9457792043685913, | |
| "eval_runtime": 112.4559, | |
| "eval_samples_per_second": 889.237, | |
| "eval_steps_per_second": 55.577, | |
| "step": 1488000 | |
| }, | |
| { | |
| "epoch": 12.6, | |
| "eval_loss": 1.9397221803665161, | |
| "eval_runtime": 111.3476, | |
| "eval_samples_per_second": 898.089, | |
| "eval_steps_per_second": 56.131, | |
| "step": 1496000 | |
| }, | |
| { | |
| "epoch": 12.67, | |
| "learning_rate": 1.5306666666666666e-07, | |
| "loss": 2.0691, | |
| "step": 1504000 | |
| }, | |
| { | |
| "epoch": 12.67, | |
| "eval_loss": 1.9437509775161743, | |
| "eval_runtime": 112.0293, | |
| "eval_samples_per_second": 892.624, | |
| "eval_steps_per_second": 55.789, | |
| "step": 1504000 | |
| }, | |
| { | |
| "epoch": 12.73, | |
| "eval_loss": 1.932470679283142, | |
| "eval_runtime": 112.2376, | |
| "eval_samples_per_second": 890.967, | |
| "eval_steps_per_second": 55.685, | |
| "step": 1512000 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 1.5033333333333332e-07, | |
| "loss": 2.0727, | |
| "step": 1520000 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "eval_loss": 1.935852289199829, | |
| "eval_runtime": 112.777, | |
| "eval_samples_per_second": 886.706, | |
| "eval_steps_per_second": 55.419, | |
| "step": 1520000 | |
| }, | |
| { | |
| "epoch": 12.87, | |
| "eval_loss": 1.9426517486572266, | |
| "eval_runtime": 112.773, | |
| "eval_samples_per_second": 886.737, | |
| "eval_steps_per_second": 55.421, | |
| "step": 1528000 | |
| }, | |
| { | |
| "epoch": 12.93, | |
| "learning_rate": 1.476e-07, | |
| "loss": 2.0715, | |
| "step": 1536000 | |
| }, | |
| { | |
| "epoch": 12.93, | |
| "eval_loss": 1.9491215944290161, | |
| "eval_runtime": 111.747, | |
| "eval_samples_per_second": 894.878, | |
| "eval_steps_per_second": 55.93, | |
| "step": 1536000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 1.9350641965866089, | |
| "eval_runtime": 111.6174, | |
| "eval_samples_per_second": 895.917, | |
| "eval_steps_per_second": 55.995, | |
| "step": 1544000 | |
| }, | |
| { | |
| "epoch": 13.07, | |
| "learning_rate": 1.4486666666666665e-07, | |
| "loss": 2.0692, | |
| "step": 1552000 | |
| }, | |
| { | |
| "epoch": 13.07, | |
| "eval_loss": 1.924606204032898, | |
| "eval_runtime": 111.7882, | |
| "eval_samples_per_second": 894.549, | |
| "eval_steps_per_second": 55.909, | |
| "step": 1552000 | |
| }, | |
| { | |
| "epoch": 13.14, | |
| "eval_loss": 1.9456748962402344, | |
| "eval_runtime": 112.0116, | |
| "eval_samples_per_second": 892.765, | |
| "eval_steps_per_second": 55.798, | |
| "step": 1560000 | |
| }, | |
| { | |
| "epoch": 13.2, | |
| "learning_rate": 1.4213333333333334e-07, | |
| "loss": 2.0711, | |
| "step": 1568000 | |
| }, | |
| { | |
| "epoch": 13.2, | |
| "eval_loss": 1.940625786781311, | |
| "eval_runtime": 111.8712, | |
| "eval_samples_per_second": 893.885, | |
| "eval_steps_per_second": 55.868, | |
| "step": 1568000 | |
| }, | |
| { | |
| "epoch": 13.27, | |
| "eval_loss": 1.9458470344543457, | |
| "eval_runtime": 113.2996, | |
| "eval_samples_per_second": 882.616, | |
| "eval_steps_per_second": 55.163, | |
| "step": 1576000 | |
| }, | |
| { | |
| "epoch": 13.34, | |
| "learning_rate": 1.3940000000000002e-07, | |
| "loss": 2.0735, | |
| "step": 1584000 | |
| }, | |
| { | |
| "epoch": 13.34, | |
| "eval_loss": 1.9356151819229126, | |
| "eval_runtime": 112.3553, | |
| "eval_samples_per_second": 890.033, | |
| "eval_steps_per_second": 55.627, | |
| "step": 1584000 | |
| }, | |
| { | |
| "epoch": 13.41, | |
| "eval_loss": 1.9443440437316895, | |
| "eval_runtime": 112.0434, | |
| "eval_samples_per_second": 892.512, | |
| "eval_steps_per_second": 55.782, | |
| "step": 1592000 | |
| }, | |
| { | |
| "epoch": 13.47, | |
| "learning_rate": 1.3666666666666665e-07, | |
| "loss": 2.0707, | |
| "step": 1600000 | |
| }, | |
| { | |
| "epoch": 13.47, | |
| "eval_loss": 1.9308792352676392, | |
| "eval_runtime": 112.2968, | |
| "eval_samples_per_second": 890.497, | |
| "eval_steps_per_second": 55.656, | |
| "step": 1600000 | |
| }, | |
| { | |
| "epoch": 13.54, | |
| "eval_loss": 1.9366567134857178, | |
| "eval_runtime": 113.834, | |
| "eval_samples_per_second": 878.472, | |
| "eval_steps_per_second": 54.904, | |
| "step": 1608000 | |
| }, | |
| { | |
| "epoch": 13.61, | |
| "learning_rate": 1.3393333333333333e-07, | |
| "loss": 2.0776, | |
| "step": 1616000 | |
| }, | |
| { | |
| "epoch": 13.61, | |
| "eval_loss": 1.938970923423767, | |
| "eval_runtime": 113.1972, | |
| "eval_samples_per_second": 883.414, | |
| "eval_steps_per_second": 55.213, | |
| "step": 1616000 | |
| }, | |
| { | |
| "epoch": 13.68, | |
| "eval_loss": 1.9390745162963867, | |
| "eval_runtime": 113.4016, | |
| "eval_samples_per_second": 881.822, | |
| "eval_steps_per_second": 55.114, | |
| "step": 1624000 | |
| }, | |
| { | |
| "epoch": 13.74, | |
| "learning_rate": 1.312e-07, | |
| "loss": 2.074, | |
| "step": 1632000 | |
| }, | |
| { | |
| "epoch": 13.74, | |
| "eval_loss": 1.945857048034668, | |
| "eval_runtime": 112.0726, | |
| "eval_samples_per_second": 892.279, | |
| "eval_steps_per_second": 55.767, | |
| "step": 1632000 | |
| }, | |
| { | |
| "epoch": 13.81, | |
| "eval_loss": 1.9315778017044067, | |
| "eval_runtime": 112.2508, | |
| "eval_samples_per_second": 890.862, | |
| "eval_steps_per_second": 55.679, | |
| "step": 1640000 | |
| }, | |
| { | |
| "epoch": 13.88, | |
| "learning_rate": 1.2846666666666667e-07, | |
| "loss": 2.0681, | |
| "step": 1648000 | |
| }, | |
| { | |
| "epoch": 13.88, | |
| "eval_loss": 1.9354796409606934, | |
| "eval_runtime": 112.1476, | |
| "eval_samples_per_second": 891.682, | |
| "eval_steps_per_second": 55.73, | |
| "step": 1648000 | |
| }, | |
| { | |
| "epoch": 13.95, | |
| "eval_loss": 1.942836046218872, | |
| "eval_runtime": 113.6141, | |
| "eval_samples_per_second": 880.172, | |
| "eval_steps_per_second": 55.011, | |
| "step": 1656000 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 1.2573333333333332e-07, | |
| "loss": 2.0671, | |
| "step": 1664000 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "eval_loss": 1.9285801649093628, | |
| "eval_runtime": 114.1501, | |
| "eval_samples_per_second": 876.04, | |
| "eval_steps_per_second": 54.752, | |
| "step": 1664000 | |
| }, | |
| { | |
| "epoch": 14.08, | |
| "eval_loss": 1.9373844861984253, | |
| "eval_runtime": 113.4911, | |
| "eval_samples_per_second": 881.126, | |
| "eval_steps_per_second": 55.07, | |
| "step": 1672000 | |
| }, | |
| { | |
| "epoch": 14.15, | |
| "learning_rate": 1.23e-07, | |
| "loss": 2.0672, | |
| "step": 1680000 | |
| }, | |
| { | |
| "epoch": 14.15, | |
| "eval_loss": 1.9412592649459839, | |
| "eval_runtime": 112.4158, | |
| "eval_samples_per_second": 889.554, | |
| "eval_steps_per_second": 55.597, | |
| "step": 1680000 | |
| }, | |
| { | |
| "epoch": 14.21, | |
| "eval_loss": 1.9371790885925293, | |
| "eval_runtime": 112.6271, | |
| "eval_samples_per_second": 887.885, | |
| "eval_steps_per_second": 55.493, | |
| "step": 1688000 | |
| }, | |
| { | |
| "epoch": 14.28, | |
| "learning_rate": 1.2026666666666666e-07, | |
| "loss": 2.0675, | |
| "step": 1696000 | |
| }, | |
| { | |
| "epoch": 14.28, | |
| "eval_loss": 1.9316694736480713, | |
| "eval_runtime": 112.9076, | |
| "eval_samples_per_second": 885.68, | |
| "eval_steps_per_second": 55.355, | |
| "step": 1696000 | |
| }, | |
| { | |
| "epoch": 14.35, | |
| "eval_loss": 1.9431692361831665, | |
| "eval_runtime": 113.2713, | |
| "eval_samples_per_second": 882.836, | |
| "eval_steps_per_second": 55.177, | |
| "step": 1704000 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "learning_rate": 1.1753333333333334e-07, | |
| "loss": 2.0665, | |
| "step": 1712000 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "eval_loss": 1.9444059133529663, | |
| "eval_runtime": 113.7863, | |
| "eval_samples_per_second": 878.841, | |
| "eval_steps_per_second": 54.928, | |
| "step": 1712000 | |
| }, | |
| { | |
| "epoch": 14.48, | |
| "eval_loss": 1.9393354654312134, | |
| "eval_runtime": 113.2214, | |
| "eval_samples_per_second": 883.225, | |
| "eval_steps_per_second": 55.202, | |
| "step": 1720000 | |
| }, | |
| { | |
| "epoch": 14.55, | |
| "learning_rate": 1.1480000000000001e-07, | |
| "loss": 2.0645, | |
| "step": 1728000 | |
| }, | |
| { | |
| "epoch": 14.55, | |
| "eval_loss": 1.9462323188781738, | |
| "eval_runtime": 114.3328, | |
| "eval_samples_per_second": 874.64, | |
| "eval_steps_per_second": 54.665, | |
| "step": 1728000 | |
| }, | |
| { | |
| "epoch": 14.62, | |
| "eval_loss": 1.9374451637268066, | |
| "eval_runtime": 112.5932, | |
| "eval_samples_per_second": 888.153, | |
| "eval_steps_per_second": 55.51, | |
| "step": 1736000 | |
| }, | |
| { | |
| "epoch": 14.69, | |
| "learning_rate": 1.1206666666666666e-07, | |
| "loss": 2.0712, | |
| "step": 1744000 | |
| }, | |
| { | |
| "epoch": 14.69, | |
| "eval_loss": 1.9367477893829346, | |
| "eval_runtime": 113.3109, | |
| "eval_samples_per_second": 882.527, | |
| "eval_steps_per_second": 55.158, | |
| "step": 1744000 | |
| }, | |
| { | |
| "epoch": 14.75, | |
| "eval_loss": 1.9407415390014648, | |
| "eval_runtime": 112.5273, | |
| "eval_samples_per_second": 888.673, | |
| "eval_steps_per_second": 55.542, | |
| "step": 1752000 | |
| }, | |
| { | |
| "epoch": 14.82, | |
| "learning_rate": 1.0933333333333333e-07, | |
| "loss": 2.0689, | |
| "step": 1760000 | |
| }, | |
| { | |
| "epoch": 14.82, | |
| "eval_loss": 1.936061978340149, | |
| "eval_runtime": 112.7649, | |
| "eval_samples_per_second": 886.801, | |
| "eval_steps_per_second": 55.425, | |
| "step": 1760000 | |
| }, | |
| { | |
| "epoch": 14.89, | |
| "eval_loss": 1.9395064115524292, | |
| "eval_runtime": 112.9027, | |
| "eval_samples_per_second": 885.719, | |
| "eval_steps_per_second": 55.357, | |
| "step": 1768000 | |
| }, | |
| { | |
| "epoch": 14.96, | |
| "learning_rate": 1.066e-07, | |
| "loss": 2.0657, | |
| "step": 1776000 | |
| }, | |
| { | |
| "epoch": 14.96, | |
| "eval_loss": 1.9389370679855347, | |
| "eval_runtime": 112.5304, | |
| "eval_samples_per_second": 888.649, | |
| "eval_steps_per_second": 55.541, | |
| "step": 1776000 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "eval_loss": 1.939638614654541, | |
| "eval_runtime": 111.9639, | |
| "eval_samples_per_second": 893.145, | |
| "eval_steps_per_second": 55.822, | |
| "step": 1784000 | |
| }, | |
| { | |
| "epoch": 15.09, | |
| "learning_rate": 1.0386666666666667e-07, | |
| "loss": 2.0781, | |
| "step": 1792000 | |
| }, | |
| { | |
| "epoch": 15.09, | |
| "eval_loss": 1.9406148195266724, | |
| "eval_runtime": 112.1285, | |
| "eval_samples_per_second": 891.834, | |
| "eval_steps_per_second": 55.74, | |
| "step": 1792000 | |
| }, | |
| { | |
| "epoch": 15.16, | |
| "eval_loss": 1.9366379976272583, | |
| "eval_runtime": 112.1351, | |
| "eval_samples_per_second": 891.781, | |
| "eval_steps_per_second": 55.736, | |
| "step": 1800000 | |
| }, | |
| { | |
| "epoch": 15.23, | |
| "learning_rate": 1.0113333333333334e-07, | |
| "loss": 2.0631, | |
| "step": 1808000 | |
| }, | |
| { | |
| "epoch": 15.23, | |
| "eval_loss": 1.935654878616333, | |
| "eval_runtime": 112.8126, | |
| "eval_samples_per_second": 886.426, | |
| "eval_steps_per_second": 55.402, | |
| "step": 1808000 | |
| }, | |
| { | |
| "epoch": 15.29, | |
| "eval_loss": 1.9456075429916382, | |
| "eval_runtime": 112.2126, | |
| "eval_samples_per_second": 891.166, | |
| "eval_steps_per_second": 55.698, | |
| "step": 1816000 | |
| }, | |
| { | |
| "epoch": 15.36, | |
| "learning_rate": 9.84e-08, | |
| "loss": 2.0738, | |
| "step": 1824000 | |
| }, | |
| { | |
| "epoch": 15.36, | |
| "eval_loss": 1.9325162172317505, | |
| "eval_runtime": 112.2554, | |
| "eval_samples_per_second": 890.825, | |
| "eval_steps_per_second": 55.677, | |
| "step": 1824000 | |
| }, | |
| { | |
| "epoch": 15.43, | |
| "eval_loss": 1.9377248287200928, | |
| "eval_runtime": 111.9986, | |
| "eval_samples_per_second": 892.868, | |
| "eval_steps_per_second": 55.804, | |
| "step": 1832000 | |
| }, | |
| { | |
| "epoch": 15.49, | |
| "learning_rate": 9.566666666666666e-08, | |
| "loss": 2.0726, | |
| "step": 1840000 | |
| }, | |
| { | |
| "epoch": 15.49, | |
| "eval_loss": 1.9404562711715698, | |
| "eval_runtime": 112.0792, | |
| "eval_samples_per_second": 892.226, | |
| "eval_steps_per_second": 55.764, | |
| "step": 1840000 | |
| }, | |
| { | |
| "epoch": 15.56, | |
| "eval_loss": 1.93331778049469, | |
| "eval_runtime": 112.9009, | |
| "eval_samples_per_second": 885.733, | |
| "eval_steps_per_second": 55.358, | |
| "step": 1848000 | |
| }, | |
| { | |
| "epoch": 15.63, | |
| "learning_rate": 9.293333333333333e-08, | |
| "loss": 2.0699, | |
| "step": 1856000 | |
| }, | |
| { | |
| "epoch": 15.63, | |
| "eval_loss": 1.936886191368103, | |
| "eval_runtime": 112.1154, | |
| "eval_samples_per_second": 891.938, | |
| "eval_steps_per_second": 55.746, | |
| "step": 1856000 | |
| }, | |
| { | |
| "epoch": 15.7, | |
| "eval_loss": 1.9418281316757202, | |
| "eval_runtime": 113.1424, | |
| "eval_samples_per_second": 883.842, | |
| "eval_steps_per_second": 55.24, | |
| "step": 1864000 | |
| }, | |
| { | |
| "epoch": 15.76, | |
| "learning_rate": 9.02e-08, | |
| "loss": 2.0764, | |
| "step": 1872000 | |
| }, | |
| { | |
| "epoch": 15.76, | |
| "eval_loss": 1.936255931854248, | |
| "eval_runtime": 112.2628, | |
| "eval_samples_per_second": 890.767, | |
| "eval_steps_per_second": 55.673, | |
| "step": 1872000 | |
| }, | |
| { | |
| "epoch": 15.83, | |
| "eval_loss": 1.9375123977661133, | |
| "eval_runtime": 113.2525, | |
| "eval_samples_per_second": 882.982, | |
| "eval_steps_per_second": 55.186, | |
| "step": 1880000 | |
| }, | |
| { | |
| "epoch": 15.9, | |
| "learning_rate": 8.746666666666667e-08, | |
| "loss": 2.0779, | |
| "step": 1888000 | |
| }, | |
| { | |
| "epoch": 15.9, | |
| "eval_loss": 1.9335252046585083, | |
| "eval_runtime": 113.7859, | |
| "eval_samples_per_second": 878.844, | |
| "eval_steps_per_second": 54.928, | |
| "step": 1888000 | |
| }, | |
| { | |
| "epoch": 15.97, | |
| "eval_loss": 1.9454823732376099, | |
| "eval_runtime": 112.4427, | |
| "eval_samples_per_second": 889.342, | |
| "eval_steps_per_second": 55.584, | |
| "step": 1896000 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 8.473333333333334e-08, | |
| "loss": 2.0693, | |
| "step": 1904000 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "eval_loss": 1.9446665048599243, | |
| "eval_runtime": 112.6559, | |
| "eval_samples_per_second": 887.659, | |
| "eval_steps_per_second": 55.479, | |
| "step": 1904000 | |
| }, | |
| { | |
| "epoch": 16.1, | |
| "eval_loss": 1.9349315166473389, | |
| "eval_runtime": 113.0201, | |
| "eval_samples_per_second": 884.798, | |
| "eval_steps_per_second": 55.3, | |
| "step": 1912000 | |
| }, | |
| { | |
| "epoch": 16.17, | |
| "learning_rate": 8.2e-08, | |
| "loss": 2.0716, | |
| "step": 1920000 | |
| }, | |
| { | |
| "epoch": 16.17, | |
| "eval_loss": 1.9339326620101929, | |
| "eval_runtime": 112.7709, | |
| "eval_samples_per_second": 886.754, | |
| "eval_steps_per_second": 55.422, | |
| "step": 1920000 | |
| }, | |
| { | |
| "epoch": 16.24, | |
| "eval_loss": 1.94255530834198, | |
| "eval_runtime": 112.798, | |
| "eval_samples_per_second": 886.54, | |
| "eval_steps_per_second": 55.409, | |
| "step": 1928000 | |
| }, | |
| { | |
| "epoch": 16.3, | |
| "learning_rate": 7.926666666666666e-08, | |
| "loss": 2.075, | |
| "step": 1936000 | |
| }, | |
| { | |
| "epoch": 16.3, | |
| "eval_loss": 1.943917155265808, | |
| "eval_runtime": 112.6881, | |
| "eval_samples_per_second": 887.405, | |
| "eval_steps_per_second": 55.463, | |
| "step": 1936000 | |
| }, | |
| { | |
| "epoch": 16.37, | |
| "eval_loss": 1.9333665370941162, | |
| "eval_runtime": 113.4627, | |
| "eval_samples_per_second": 881.347, | |
| "eval_steps_per_second": 55.084, | |
| "step": 1944000 | |
| }, | |
| { | |
| "epoch": 16.44, | |
| "learning_rate": 7.653333333333333e-08, | |
| "loss": 2.0751, | |
| "step": 1952000 | |
| }, | |
| { | |
| "epoch": 16.44, | |
| "eval_loss": 1.9466158151626587, | |
| "eval_runtime": 112.5622, | |
| "eval_samples_per_second": 888.398, | |
| "eval_steps_per_second": 55.525, | |
| "step": 1952000 | |
| }, | |
| { | |
| "epoch": 16.51, | |
| "eval_loss": 1.9396798610687256, | |
| "eval_runtime": 112.8587, | |
| "eval_samples_per_second": 886.064, | |
| "eval_steps_per_second": 55.379, | |
| "step": 1960000 | |
| }, | |
| { | |
| "epoch": 16.57, | |
| "learning_rate": 7.38e-08, | |
| "loss": 2.0734, | |
| "step": 1968000 | |
| }, | |
| { | |
| "epoch": 16.57, | |
| "eval_loss": 1.9367443323135376, | |
| "eval_runtime": 113.0019, | |
| "eval_samples_per_second": 884.941, | |
| "eval_steps_per_second": 55.309, | |
| "step": 1968000 | |
| }, | |
| { | |
| "epoch": 16.64, | |
| "eval_loss": 1.9348819255828857, | |
| "eval_runtime": 113.2526, | |
| "eval_samples_per_second": 882.982, | |
| "eval_steps_per_second": 55.186, | |
| "step": 1976000 | |
| }, | |
| { | |
| "epoch": 16.71, | |
| "learning_rate": 7.106666666666667e-08, | |
| "loss": 2.0685, | |
| "step": 1984000 | |
| }, | |
| { | |
| "epoch": 16.71, | |
| "eval_loss": 1.950958013534546, | |
| "eval_runtime": 112.2498, | |
| "eval_samples_per_second": 890.87, | |
| "eval_steps_per_second": 55.679, | |
| "step": 1984000 | |
| }, | |
| { | |
| "epoch": 16.77, | |
| "eval_loss": 1.9427640438079834, | |
| "eval_runtime": 112.1897, | |
| "eval_samples_per_second": 891.347, | |
| "eval_steps_per_second": 55.709, | |
| "step": 1992000 | |
| }, | |
| { | |
| "epoch": 16.84, | |
| "learning_rate": 6.833333333333332e-08, | |
| "loss": 2.0706, | |
| "step": 2000000 | |
| }, | |
| { | |
| "epoch": 16.84, | |
| "eval_loss": 1.9509494304656982, | |
| "eval_runtime": 112.3131, | |
| "eval_samples_per_second": 890.368, | |
| "eval_steps_per_second": 55.648, | |
| "step": 2000000 | |
| }, | |
| { | |
| "epoch": 16.91, | |
| "eval_loss": 1.9403355121612549, | |
| "eval_runtime": 112.559, | |
| "eval_samples_per_second": 888.423, | |
| "eval_steps_per_second": 55.526, | |
| "step": 2008000 | |
| }, | |
| { | |
| "epoch": 16.98, | |
| "learning_rate": 6.56e-08, | |
| "loss": 2.0716, | |
| "step": 2016000 | |
| }, | |
| { | |
| "epoch": 16.98, | |
| "eval_loss": 1.9383665323257446, | |
| "eval_runtime": 113.2638, | |
| "eval_samples_per_second": 882.894, | |
| "eval_steps_per_second": 55.181, | |
| "step": 2016000 | |
| }, | |
| { | |
| "epoch": 17.04, | |
| "eval_loss": 1.935543179512024, | |
| "eval_runtime": 113.0174, | |
| "eval_samples_per_second": 884.819, | |
| "eval_steps_per_second": 55.301, | |
| "step": 2024000 | |
| }, | |
| { | |
| "epoch": 17.11, | |
| "learning_rate": 6.286666666666666e-08, | |
| "loss": 2.0741, | |
| "step": 2032000 | |
| }, | |
| { | |
| "epoch": 17.11, | |
| "eval_loss": 1.9308490753173828, | |
| "eval_runtime": 113.1785, | |
| "eval_samples_per_second": 883.56, | |
| "eval_steps_per_second": 55.223, | |
| "step": 2032000 | |
| }, | |
| { | |
| "epoch": 17.18, | |
| "eval_loss": 1.9395028352737427, | |
| "eval_runtime": 113.293, | |
| "eval_samples_per_second": 882.667, | |
| "eval_steps_per_second": 55.167, | |
| "step": 2040000 | |
| }, | |
| { | |
| "epoch": 17.25, | |
| "learning_rate": 6.013333333333333e-08, | |
| "loss": 2.0714, | |
| "step": 2048000 | |
| }, | |
| { | |
| "epoch": 17.25, | |
| "eval_loss": 1.9502129554748535, | |
| "eval_runtime": 113.0063, | |
| "eval_samples_per_second": 884.907, | |
| "eval_steps_per_second": 55.307, | |
| "step": 2048000 | |
| }, | |
| { | |
| "epoch": 17.31, | |
| "eval_loss": 1.9337003231048584, | |
| "eval_runtime": 114.7888, | |
| "eval_samples_per_second": 871.165, | |
| "eval_steps_per_second": 54.448, | |
| "step": 2056000 | |
| }, | |
| { | |
| "epoch": 17.38, | |
| "learning_rate": 5.7400000000000004e-08, | |
| "loss": 2.0696, | |
| "step": 2064000 | |
| }, | |
| { | |
| "epoch": 17.38, | |
| "eval_loss": 1.9382506608963013, | |
| "eval_runtime": 113.6067, | |
| "eval_samples_per_second": 880.23, | |
| "eval_steps_per_second": 55.014, | |
| "step": 2064000 | |
| }, | |
| { | |
| "epoch": 17.45, | |
| "eval_loss": 1.9450607299804688, | |
| "eval_runtime": 113.2107, | |
| "eval_samples_per_second": 883.309, | |
| "eval_steps_per_second": 55.207, | |
| "step": 2072000 | |
| }, | |
| { | |
| "epoch": 17.52, | |
| "learning_rate": 5.4666666666666666e-08, | |
| "loss": 2.0729, | |
| "step": 2080000 | |
| }, | |
| { | |
| "epoch": 17.52, | |
| "eval_loss": 1.9372721910476685, | |
| "eval_runtime": 113.4098, | |
| "eval_samples_per_second": 881.758, | |
| "eval_steps_per_second": 55.11, | |
| "step": 2080000 | |
| }, | |
| { | |
| "epoch": 17.58, | |
| "eval_loss": 1.9365758895874023, | |
| "eval_runtime": 112.5019, | |
| "eval_samples_per_second": 888.874, | |
| "eval_steps_per_second": 55.555, | |
| "step": 2088000 | |
| }, | |
| { | |
| "epoch": 17.65, | |
| "learning_rate": 5.1933333333333335e-08, | |
| "loss": 2.0716, | |
| "step": 2096000 | |
| }, | |
| { | |
| "epoch": 17.65, | |
| "eval_loss": 1.933381199836731, | |
| "eval_runtime": 113.0267, | |
| "eval_samples_per_second": 884.746, | |
| "eval_steps_per_second": 55.297, | |
| "step": 2096000 | |
| }, | |
| { | |
| "epoch": 17.72, | |
| "eval_loss": 1.9417020082473755, | |
| "eval_runtime": 113.1566, | |
| "eval_samples_per_second": 883.731, | |
| "eval_steps_per_second": 55.233, | |
| "step": 2104000 | |
| }, | |
| { | |
| "epoch": 17.79, | |
| "learning_rate": 4.92e-08, | |
| "loss": 2.074, | |
| "step": 2112000 | |
| }, | |
| { | |
| "epoch": 17.79, | |
| "eval_loss": 1.9408122301101685, | |
| "eval_runtime": 112.4418, | |
| "eval_samples_per_second": 889.349, | |
| "eval_steps_per_second": 55.584, | |
| "step": 2112000 | |
| }, | |
| { | |
| "epoch": 17.85, | |
| "eval_loss": 1.9258335828781128, | |
| "eval_runtime": 113.2063, | |
| "eval_samples_per_second": 883.343, | |
| "eval_steps_per_second": 55.209, | |
| "step": 2120000 | |
| }, | |
| { | |
| "epoch": 17.92, | |
| "learning_rate": 4.6466666666666666e-08, | |
| "loss": 2.0745, | |
| "step": 2128000 | |
| }, | |
| { | |
| "epoch": 17.92, | |
| "eval_loss": 1.938525915145874, | |
| "eval_runtime": 114.1896, | |
| "eval_samples_per_second": 875.736, | |
| "eval_steps_per_second": 54.734, | |
| "step": 2128000 | |
| }, | |
| { | |
| "epoch": 17.99, | |
| "eval_loss": 1.9408940076828003, | |
| "eval_runtime": 114.808, | |
| "eval_samples_per_second": 871.019, | |
| "eval_steps_per_second": 54.439, | |
| "step": 2136000 | |
| }, | |
| { | |
| "epoch": 18.05, | |
| "learning_rate": 4.3733333333333335e-08, | |
| "loss": 2.074, | |
| "step": 2144000 | |
| }, | |
| { | |
| "epoch": 18.05, | |
| "eval_loss": 1.9341570138931274, | |
| "eval_runtime": 113.4257, | |
| "eval_samples_per_second": 881.634, | |
| "eval_steps_per_second": 55.102, | |
| "step": 2144000 | |
| }, | |
| { | |
| "epoch": 18.12, | |
| "eval_loss": 1.9437114000320435, | |
| "eval_runtime": 113.6847, | |
| "eval_samples_per_second": 879.626, | |
| "eval_steps_per_second": 54.977, | |
| "step": 2152000 | |
| }, | |
| { | |
| "epoch": 18.19, | |
| "learning_rate": 4.1e-08, | |
| "loss": 2.0666, | |
| "step": 2160000 | |
| }, | |
| { | |
| "epoch": 18.19, | |
| "eval_loss": 1.9405776262283325, | |
| "eval_runtime": 112.7306, | |
| "eval_samples_per_second": 887.071, | |
| "eval_steps_per_second": 55.442, | |
| "step": 2160000 | |
| }, | |
| { | |
| "epoch": 18.26, | |
| "eval_loss": 1.9382190704345703, | |
| "eval_runtime": 112.7331, | |
| "eval_samples_per_second": 887.051, | |
| "eval_steps_per_second": 55.441, | |
| "step": 2168000 | |
| }, | |
| { | |
| "epoch": 18.32, | |
| "learning_rate": 3.8266666666666665e-08, | |
| "loss": 2.0657, | |
| "step": 2176000 | |
| }, | |
| { | |
| "epoch": 18.32, | |
| "eval_loss": 1.939794659614563, | |
| "eval_runtime": 112.8451, | |
| "eval_samples_per_second": 886.17, | |
| "eval_steps_per_second": 55.386, | |
| "step": 2176000 | |
| }, | |
| { | |
| "epoch": 18.39, | |
| "eval_loss": 1.9246890544891357, | |
| "eval_runtime": 112.9742, | |
| "eval_samples_per_second": 885.158, | |
| "eval_steps_per_second": 55.322, | |
| "step": 2184000 | |
| }, | |
| { | |
| "epoch": 18.46, | |
| "learning_rate": 3.5533333333333334e-08, | |
| "loss": 2.0692, | |
| "step": 2192000 | |
| }, | |
| { | |
| "epoch": 18.46, | |
| "eval_loss": 1.9376510381698608, | |
| "eval_runtime": 113.0265, | |
| "eval_samples_per_second": 884.748, | |
| "eval_steps_per_second": 55.297, | |
| "step": 2192000 | |
| }, | |
| { | |
| "epoch": 18.53, | |
| "eval_loss": 1.942256212234497, | |
| "eval_runtime": 113.1034, | |
| "eval_samples_per_second": 884.147, | |
| "eval_steps_per_second": 55.259, | |
| "step": 2200000 | |
| }, | |
| { | |
| "epoch": 18.59, | |
| "learning_rate": 3.28e-08, | |
| "loss": 2.0726, | |
| "step": 2208000 | |
| }, | |
| { | |
| "epoch": 18.59, | |
| "eval_loss": 1.9394909143447876, | |
| "eval_runtime": 113.55, | |
| "eval_samples_per_second": 880.669, | |
| "eval_steps_per_second": 55.042, | |
| "step": 2208000 | |
| }, | |
| { | |
| "epoch": 18.66, | |
| "eval_loss": 1.9286389350891113, | |
| "eval_runtime": 112.8956, | |
| "eval_samples_per_second": 885.774, | |
| "eval_steps_per_second": 55.361, | |
| "step": 2216000 | |
| }, | |
| { | |
| "epoch": 18.73, | |
| "learning_rate": 3.0066666666666665e-08, | |
| "loss": 2.0688, | |
| "step": 2224000 | |
| }, | |
| { | |
| "epoch": 18.73, | |
| "eval_loss": 1.9356930255889893, | |
| "eval_runtime": 113.4246, | |
| "eval_samples_per_second": 881.643, | |
| "eval_steps_per_second": 55.103, | |
| "step": 2224000 | |
| }, | |
| { | |
| "epoch": 18.8, | |
| "eval_loss": 1.9267104864120483, | |
| "eval_runtime": 112.8211, | |
| "eval_samples_per_second": 886.359, | |
| "eval_steps_per_second": 55.397, | |
| "step": 2232000 | |
| }, | |
| { | |
| "epoch": 18.86, | |
| "learning_rate": 2.7333333333333333e-08, | |
| "loss": 2.0732, | |
| "step": 2240000 | |
| }, | |
| { | |
| "epoch": 18.86, | |
| "eval_loss": 1.929336428642273, | |
| "eval_runtime": 112.5503, | |
| "eval_samples_per_second": 888.492, | |
| "eval_steps_per_second": 55.531, | |
| "step": 2240000 | |
| }, | |
| { | |
| "epoch": 18.93, | |
| "eval_loss": 1.941459059715271, | |
| "eval_runtime": 113.4202, | |
| "eval_samples_per_second": 881.677, | |
| "eval_steps_per_second": 55.105, | |
| "step": 2248000 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 2.46e-08, | |
| "loss": 2.0697, | |
| "step": 2256000 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 1.9455673694610596, | |
| "eval_runtime": 113.6851, | |
| "eval_samples_per_second": 879.623, | |
| "eval_steps_per_second": 54.976, | |
| "step": 2256000 | |
| }, | |
| { | |
| "epoch": 19.07, | |
| "eval_loss": 1.9331035614013672, | |
| "eval_runtime": 113.8097, | |
| "eval_samples_per_second": 878.66, | |
| "eval_steps_per_second": 54.916, | |
| "step": 2264000 | |
| }, | |
| { | |
| "epoch": 19.13, | |
| "learning_rate": 2.1866666666666667e-08, | |
| "loss": 2.0747, | |
| "step": 2272000 | |
| }, | |
| { | |
| "epoch": 19.13, | |
| "eval_loss": 1.9439350366592407, | |
| "eval_runtime": 112.8451, | |
| "eval_samples_per_second": 886.17, | |
| "eval_steps_per_second": 55.386, | |
| "step": 2272000 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "eval_loss": 1.9293532371520996, | |
| "eval_runtime": 113.0471, | |
| "eval_samples_per_second": 884.587, | |
| "eval_steps_per_second": 55.287, | |
| "step": 2280000 | |
| }, | |
| { | |
| "epoch": 19.27, | |
| "learning_rate": 1.9133333333333333e-08, | |
| "loss": 2.072, | |
| "step": 2288000 | |
| }, | |
| { | |
| "epoch": 19.27, | |
| "eval_loss": 1.930493950843811, | |
| "eval_runtime": 114.1854, | |
| "eval_samples_per_second": 875.769, | |
| "eval_steps_per_second": 54.736, | |
| "step": 2288000 | |
| }, | |
| { | |
| "epoch": 19.33, | |
| "eval_loss": 1.9400615692138672, | |
| "eval_runtime": 114.2764, | |
| "eval_samples_per_second": 875.071, | |
| "eval_steps_per_second": 54.692, | |
| "step": 2296000 | |
| }, | |
| { | |
| "epoch": 19.4, | |
| "learning_rate": 1.64e-08, | |
| "loss": 2.0609, | |
| "step": 2304000 | |
| }, | |
| { | |
| "epoch": 19.4, | |
| "eval_loss": 1.9361680746078491, | |
| "eval_runtime": 113.6148, | |
| "eval_samples_per_second": 880.167, | |
| "eval_steps_per_second": 55.01, | |
| "step": 2304000 | |
| }, | |
| { | |
| "epoch": 19.47, | |
| "eval_loss": 1.945052146911621, | |
| "eval_runtime": 113.9383, | |
| "eval_samples_per_second": 877.668, | |
| "eval_steps_per_second": 54.854, | |
| "step": 2312000 | |
| }, | |
| { | |
| "epoch": 19.54, | |
| "learning_rate": 1.3666666666666667e-08, | |
| "loss": 2.073, | |
| "step": 2320000 | |
| }, | |
| { | |
| "epoch": 19.54, | |
| "eval_loss": 1.9352370500564575, | |
| "eval_runtime": 113.3806, | |
| "eval_samples_per_second": 881.985, | |
| "eval_steps_per_second": 55.124, | |
| "step": 2320000 | |
| }, | |
| { | |
| "epoch": 19.6, | |
| "eval_loss": 1.9379993677139282, | |
| "eval_runtime": 113.7775, | |
| "eval_samples_per_second": 878.908, | |
| "eval_steps_per_second": 54.932, | |
| "step": 2328000 | |
| }, | |
| { | |
| "epoch": 19.67, | |
| "learning_rate": 1.0933333333333334e-08, | |
| "loss": 2.0793, | |
| "step": 2336000 | |
| }, | |
| { | |
| "epoch": 19.67, | |
| "eval_loss": 1.9392181634902954, | |
| "eval_runtime": 114.1447, | |
| "eval_samples_per_second": 876.081, | |
| "eval_steps_per_second": 54.755, | |
| "step": 2336000 | |
| }, | |
| { | |
| "epoch": 19.74, | |
| "eval_loss": 1.943751573562622, | |
| "eval_runtime": 113.0391, | |
| "eval_samples_per_second": 884.65, | |
| "eval_steps_per_second": 55.291, | |
| "step": 2344000 | |
| }, | |
| { | |
| "epoch": 19.81, | |
| "learning_rate": 8.2e-09, | |
| "loss": 2.0787, | |
| "step": 2352000 | |
| }, | |
| { | |
| "epoch": 19.81, | |
| "eval_loss": 1.9403409957885742, | |
| "eval_runtime": 113.8554, | |
| "eval_samples_per_second": 878.307, | |
| "eval_steps_per_second": 54.894, | |
| "step": 2352000 | |
| }, | |
| { | |
| "epoch": 19.87, | |
| "eval_loss": 1.9380377531051636, | |
| "eval_runtime": 112.993, | |
| "eval_samples_per_second": 885.011, | |
| "eval_steps_per_second": 55.313, | |
| "step": 2360000 | |
| }, | |
| { | |
| "epoch": 19.94, | |
| "learning_rate": 5.466666666666667e-09, | |
| "loss": 2.0694, | |
| "step": 2368000 | |
| }, | |
| { | |
| "epoch": 19.94, | |
| "eval_loss": 1.9274845123291016, | |
| "eval_runtime": 113.327, | |
| "eval_samples_per_second": 882.402, | |
| "eval_steps_per_second": 55.15, | |
| "step": 2368000 | |
| }, | |
| { | |
| "epoch": 20.01, | |
| "eval_loss": 1.9343926906585693, | |
| "eval_runtime": 113.0299, | |
| "eval_samples_per_second": 884.722, | |
| "eval_steps_per_second": 55.295, | |
| "step": 2376000 | |
| }, | |
| { | |
| "epoch": 20.08, | |
| "learning_rate": 2.7333333333333334e-09, | |
| "loss": 2.0649, | |
| "step": 2384000 | |
| }, | |
| { | |
| "epoch": 20.08, | |
| "eval_loss": 1.944276213645935, | |
| "eval_runtime": 113.1534, | |
| "eval_samples_per_second": 883.756, | |
| "eval_steps_per_second": 55.235, | |
| "step": 2384000 | |
| }, | |
| { | |
| "epoch": 20.14, | |
| "eval_loss": 1.9400659799575806, | |
| "eval_runtime": 113.9859, | |
| "eval_samples_per_second": 877.302, | |
| "eval_steps_per_second": 54.831, | |
| "step": 2392000 | |
| }, | |
| { | |
| "epoch": 20.21, | |
| "learning_rate": 0.0, | |
| "loss": 2.0727, | |
| "step": 2400000 | |
| }, | |
| { | |
| "epoch": 20.21, | |
| "eval_loss": 1.9447115659713745, | |
| "eval_runtime": 113.1722, | |
| "eval_samples_per_second": 883.609, | |
| "eval_steps_per_second": 55.226, | |
| "step": 2400000 | |
| }, | |
| { | |
| "epoch": 20.21, | |
| "step": 2400000, | |
| "total_flos": 7.569354466725706e+17, | |
| "train_loss": 2.08237556640625, | |
| "train_runtime": 186458.4438, | |
| "train_samples_per_second": 205.944, | |
| "train_steps_per_second": 12.872 | |
| } | |
| ], | |
| "logging_steps": 16000, | |
| "max_steps": 2400000, | |
| "num_train_epochs": 21, | |
| "save_steps": 32000, | |
| "total_flos": 7.569354466725706e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |